Skip to main content

2021 | OriginalPaper | Buchkapitel

Invertible Neural Networks Versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence

verfasst von : Anna Andrle, Nando Farchmin, Paul Hagemann, Sebastian Heidenreich, Victor Soltwisch, Gabriele Steidl

Erschienen in: Scale Space and Variational Methods in Computer Vision

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Grazing incidence X-ray fluorescence is a non-destructive technique for analyzing the geometry and compositional parameters of nanostructures appearing e.g. in computer chips. In this paper, we propose to reconstruct the posterior parameter distribution given a noisy measurement generated by the forward model by an appropriately learned invertible neural network. This network resembles the transport map from a reference distribution to the posterior. We demonstrate by numerical comparisons that our method can compete with established Markov Chain Monte Carlo approaches, while being more efficient and flexible in applications.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Andrieu, C., de Freitas, N., Doucet, A., Jordan, M.I.: An introduction to MCMC for machine learning. Mach. Learn. 50, 5–43 (2003)CrossRef Andrieu, C., de Freitas, N., Doucet, A., Jordan, M.I.: An introduction to MCMC for machine learning. Mach. Learn. 50, 5–43 (2003)CrossRef
2.
Zurück zum Zitat Andrle, A., et al.: Grazing incidence x-ray fluorescence based characterization of nanostructures for element sensitive profile reconstruction. In: Modeling Aspects in Optical Metrology VII, vol. 11057, p. 110570M. International Society for Optics and Photonics (2019) Andrle, A., et al.: Grazing incidence x-ray fluorescence based characterization of nanostructures for element sensitive profile reconstruction. In: Modeling Aspects in Optical Metrology VII, vol. 11057, p. 110570M. International Society for Optics and Photonics (2019)
3.
Zurück zum Zitat Ardizzone, L., Kruse, J., Rother, C., Köthe, U.: Analyzing inverse problems with invertible neural networks. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, (2019) Ardizzone, L., Kruse, J., Rother, C., Köthe, U.: Analyzing inverse problems with invertible neural networks. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, (2019)
4.
Zurück zum Zitat Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings (2017) Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings (2017)
5.
Zurück zum Zitat Foreman-Mackey, D., Hogg, D.W., Lang, D., Goodman, J.: EMCEE: the MCMC hammer. Publ. Astron. Soc. Pacific 125(925), 306–312 (2013)CrossRef Foreman-Mackey, D., Hogg, D.W., Lang, D., Goodman, J.: EMCEE: the MCMC hammer. Publ. Astron. Soc. Pacific 125(925), 306–312 (2013)CrossRef
6.
Zurück zum Zitat Hagemann, P.L., Neumayer, S.: Stabilizing invertible neural networks using mixture models. Inverse Problems (2021) Hagemann, P.L., Neumayer, S.: Stabilizing invertible neural networks using mixture models. Inverse Problems (2021)
7.
Zurück zum Zitat Henn, M.-A., Gross, H., Heidenreich, S., Scholze, F., Elster, C., Bär, M.: Improved reconstruction of critical dimensions in extreme ultraviolet scatterometry by modeling systematic errors. Meas. Sci. Technol. 25(4), 044003/1–9 (2014) Henn, M.-A., Gross, H., Heidenreich, S., Scholze, F., Elster, C., Bär, M.: Improved reconstruction of critical dimensions in extreme ultraviolet scatterometry by modeling systematic errors. Meas. Sci. Technol. 25(4), 044003/1–9 (2014)
8.
Zurück zum Zitat Hönicke, P., et al.: Grazing incidence-x-ray fluorescence for a dimensional and compositional characterization of well-ordered 2D and 3D nanostructures. Nanotechnology 31(50), 505709/1–8 (2020) Hönicke, P., et al.: Grazing incidence-x-ray fluorescence for a dimensional and compositional characterization of well-ordered 2D and 3D nanostructures. Nanotechnology 31(50), 505709/1–8 (2020)
9.
Zurück zum Zitat Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings (2015) Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings (2015)
10.
Zurück zum Zitat Kruse, J., Detommaso, G., Scheichl, R., Köthe, U.: HINT: hierarchical invertible neural transport for density estimation and Bayesian inference. arXiv preprint arXiv:1905.10687 (2020) Kruse, J., Detommaso, G., Scheichl, R., Köthe, U.: HINT: hierarchical invertible neural transport for density estimation and Bayesian inference. arXiv preprint arXiv:​1905.​10687 (2020)
11.
Zurück zum Zitat Mack, C.: Fundamental principles of optical lithography: the science of microfabrication. John Wiley & Sons (2008) Mack, C.: Fundamental principles of optical lithography: the science of microfabrication. John Wiley & Sons (2008)
12.
Zurück zum Zitat Marzouk, Y., Moselhy, T., Parno, M., Spantini, A.: Sampling via measure transport: an introduction. Handbook of Uncertainty Quantification, pp. 1–41 (2016) Marzouk, Y., Moselhy, T., Parno, M., Spantini, A.: Sampling via measure transport: an introduction. Handbook of Uncertainty Quantification, pp. 1–41 (2016)
13.
Zurück zum Zitat Pomplun, J., Burger, S., Zschiedrich, L., Schmidt, F.: Adaptive finite element method for simulation of optical nano structures. Phys. Status Solidi (B) 244(10), 3419–3434 (2007)CrossRef Pomplun, J., Burger, S., Zschiedrich, L., Schmidt, F.: Adaptive finite element method for simulation of optical nano structures. Phys. Status Solidi (B) 244(10), 3419–3434 (2007)CrossRef
14.
Zurück zum Zitat Rizzuti, G., Siahkoohi, A., Witte, P., Herrmann, F.: Parameterizing uncertainty by deep invertible networks: an application to reservoir characterization. SEG Tech. Program Expanded Abs. 2020, 1541–1545 (2020) Rizzuti, G., Siahkoohi, A., Witte, P., Herrmann, F.: Parameterizing uncertainty by deep invertible networks: an application to reservoir characterization. SEG Tech. Program Expanded Abs. 2020, 1541–1545 (2020)
15.
Zurück zum Zitat Rudin., W.: Real Analysis. McGraw-Hill, 3rd edition (1987) Rudin., W.: Real Analysis. McGraw-Hill, 3rd edition (1987)
16.
Zurück zum Zitat Siahkoohi, A., Rizzuti, G., Louboutin, M., Witte, P., Herrmann, F.J.: Preconditioned training of normalizing flows for variational inference in inverse problems. In: 3rd Symposium on Advances in Approximate Bayesian Inference (2021) Siahkoohi, A., Rizzuti, G., Louboutin, M., Witte, P., Herrmann, F.J.: Preconditioned training of normalizing flows for variational inference in inverse problems. In: 3rd Symposium on Advances in Approximate Bayesian Inference (2021)
17.
Zurück zum Zitat Soltwisch, V., et al.: Element sensitive reconstruction of nanostructured surfaces with finite elements and grazing incidence soft x-ray fluorescence. Nanoscale 10(13), 6177–6185 (2018)CrossRef Soltwisch, V., et al.: Element sensitive reconstruction of nanostructured surfaces with finite elements and grazing incidence soft x-ray fluorescence. Nanoscale 10(13), 6177–6185 (2018)CrossRef
Metadaten
Titel
Invertible Neural Networks Versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence
verfasst von
Anna Andrle
Nando Farchmin
Paul Hagemann
Sebastian Heidenreich
Victor Soltwisch
Gabriele Steidl
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-75549-2_42